About Medux
Medux is a hosted MCP server for AI assistants that generate or edit media. Its 60+ tools cover video, images, speech, voice cloning, avatars, and PDF, audio, and video processing.
Key features
- 01Generate video and images
- 02Generate speech and clone voices
- 03Create avatars
- 04Edit and convert PDF, audio, and video
- 05Query task status
Use cases
- 01Generate media through an AI assistant
- 02Clone a voice or create an avatar
- 03Edit or convert PDF, audio, or video
- 04Check the progress of a media task
MCP support
Provides 60+ media generation, editing, conversion, and task-query tools through a streamable HTTP MCP endpoint. Clients authenticate with a bearer API key.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://medux.io/api/mcp/v1claude mcp add --transport http meduxio-medux https://medux.io/api/mcp/v1{"mcpServers":{"meduxio-medux":{"type":"http","url":"https://medux.io/api/mcp/v1"}}}Open in Cursor{"servers":{"meduxio-medux":{"type":"http","url":"https://medux.io/api/mcp/v1"}}}Open in VS Code{"mcpServers":{"meduxio-medux":{"type":"http","url":"https://medux.io/api/mcp/v1"}}}{"mcpServers":{"meduxio-medux":{"serverUrl":"https://medux.io/api/mcp/v1"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://medux.io/api/mcp/v1Auth requiredTools
Details
From the project READMEMedux MCP Server
Connect AI assistants to Medux for AI media generation and editing: video, image, speech, voice cloning, avatars, and PDF/audio/video tools.
- Endpoint (streamable HTTP):
https://medux.io/api/mcp/v1 - Authentication:
Authorization: Bearer sk-medux-... - Tools: 60+ (generation, editing, conversion, task query)
1. Get an API key
Create an API key (starts with sk-medux-) in your Medux account at https://medux.io.
Keep it secret; do not commit it to a repository.
2. GitHub Copilot / VS Code
Requires VS Code with GitHub Copilot signed in, and Copilot Chat in Agent mode.
-
Run MCP: Open User Configuration from the Command Palette (⇧⌘P / Ctrl+Shift+P).
-
Add the server:
{ "servers": { "medux": { "type": "http", "url": "https://medux.io/api/mcp/v1", "headers": { "Authorization": "Bearer ${input:medux-api-key}" } } }, "inputs": [ { "type": "promptString", "id": "medux-api-key", "description": "Medux API key", "password": true } ] } -
In the MCP Servers list, open the gear next to
meduxand choose Start Server (or Restart Server). -
In Copilot Chat (Agent mode) open the tools picker and confirm the
meduxtools are listed. -
Try a harmless request first, for example: "Use medux to list what you can do".
If the key prompt never appears
In some setups VS Code does not show the ${input:...} prompt, and tool calls end with Canceled or 401.
Replace the header value with your key directly in your user-level mcp.json (never in a repository):
"headers": { "Authorization": "Bearer sk-medux-xxxxxxxx" }
Then restart the server.
Troubleshooting
| Symptom | Likely cause |
|---|---|
401 / unauthorized | Missing Bearer prefix, wrong or revoked key |
Canceled: Canceled on every call | The key prompt was not answered; use the direct-header form above |
404 with NOT_FOUND | The request reached Medux; the task or resource id does not exist |
| Server not listed | Check MCP: Open User Configuration saved correctly; view logs via the gear → Show Output |
Registry
Published to the MCP Registry as io.github.MeduxIO/medux
through .github/workflows/publish-mcp.yml (GitHub OIDC).
To release a new version: bump version in server.json, then run the workflow or push a v* tag.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.